When I use tensorboard to show the data, I found that there is more than one curve. I think this is related to the configuration. So could someone tell me what each curve represents?
This is not related in any way with the Cloud ML Engine. You can find
all the configurable parameters for the Engine in the docs for its REST API (training input, training output, prediction input, prediction output, model resource, version resource).
These curves from your tensorboard is something you configured in your tensorflow code, probably the training cost for several different runs, set as a summary scalar with the name "train_cost".
Related
I want to know if there is any basic difference between how spacy_sklearn and tensorflow_embedding pipelines operate under the hood.I mean tensorflow_embedding must also be using the same concepts of word embeddings,reducing the dimensionality of data using PCA etc. Is the only difference then that spacy_sklearn has some pre trained data to draw upon in the form of pre trained vectors and tensorflow pipeline does not?Is my understanding correct?Also how is tensorflow_embedding pipeline related to the tensorflow framework offered by google?
I tried looking up tensorflow framework on google, but could not get any specific answer.I also searched about it on RASA community page, but again found no help
The spacy_sklearn pipeline uses pre-trained word vectors.This is useful if we don’t have very much training data.
The tensorflow embedding pipeline doesn’t use any pre-trained word vectors,it fits specifically for our dataset. The advantage of the tensorflow_embedding pipeline is that the word vectors will be customised for our domain.
For more information ,please refer the below link
https://rasa.com/docs/nlu/choosing_pipeline/
I currently pre-process some data on my laptop before passing it to ML Engine for training. Is it possible to apply a custom pre-processing function to my data and then train, all within ML Engine?
So instead of these steps:
Pre-process data on laptop.
Send pre-processed data to ML engine for training.
I would do:
Define pre-processing function for ML Engine
Send raw data to ML Engine, where it will:
a) pre-process my data by applying the function I've specified and
b) train on that data
Is this possible and, if so, how would I do it? I don't see anything in the docs.
Thanks!
You can use some of the samples code here:
Pre-processing is done using DataFlow and then training in ML Engine using the output generated during the pre-process phase.
For preprocessing TensorFlow models, consider TensorFlow Transform (Getting Started Guide).
You may be interested in the chicago_taxi example, which includes a script for integrating the preprocessing with classification on Cloud ML Engine.
So as a fun project, I've been messing with the TensorFlow API (in Java unfortunately.. but I should be able to get some results out anyways). My first goal is to develop a model for 2D point cloud filtering. So I have written code that generates random clouds in 224x172 resolution, computes the result of a neighbor density filter, and stores both (see images below).
So basically I have generated data for both an input and expected output, which can be done as much as needed for a massive dataset.
I have both the input and output arrays stored as 224x172 binary arrays (0 for no point at index, 1 for a point at that index). So my input and output are both 224x172. At this point, I'm not sure how to translate my input to my expected result. I'm not sure how to weight each "pixel" of my cloud, or how to "teach" the program the expected result. Any suggestions/guidance on whether this is even possible for my given scenario would be appreciated!
Please don't be too hard on me... I'm a complete noob when it comes to machine learning.
Imagine, that Tensorflow is a set of building blocks (like LEGO) that allows constructing machine learning models. After the model is constructed, it could be trained and evaluated.
So basically your question could be divided into three steps:
1. I'm new to machine learning. Please guide me how to choose the model that fits the task.
2. I'm new to tensorflow. I have the idea of model (see 1) and I want to construct it via Tensorflow.
3. I'm new to Java's API of tensorflow. I know how to build model using tensorflow (2), but I'm stuck in Java.
This sounds scaring, but that's not too bad really. And I'd suggest you the following plan to do:
1. You need to look through the machine learning models to find the model that suits your case. So you need to ask yourself: what are the models that could be used for cloud filtering? And basically, do you really need some machine learning model? Why don't you use simple math formulas?
That are the questions you may ask to yourself.
Ok, assume you've found some model. For example, you've found a paper describing neural network able to solve your tasks. Then go to the next step
2. Tensorflow has a lot of examples and code snippets. So you could even
find the code with your model implemented yet.
The bad thing, that most code examples and API are Python based. But as you want to go into machine learning, I'd suggest you studying Python. It's easy to enter. It's very common to use python in the science world as it allows not to waste time on wrappers, configuration, etc. (as Java needs). We just start solving our task from the first line of the script.
As I've told initially about tensorflow and LEGO similarity, I'd like to add that there are more high-level additions to the tensorflow. So you work with the not building blocks but some kind of layers of blocks.
Something like tflearn. It's very good especially if you don't have deep math or machine learning background. It allows building machine learning models in a very simple and understandable way. So do you need to add some neural network layer? Here you are. And that's all without complex low-level tensor operations.
The disadvantage that you won't be able to load tflearn model from Java.
Anyway, we assume, at the end of this step you are able to build your model, to train it and to evaluate the model and prediction quality.
3. So you have your machine learning model, you understand Tensorflow mechanics, and if you still need to work with Java that should be much easier yet.
I note, that you won't be able to load tflearn model from Java. You can try to use jython to call python's functions directly from Java, though I haven't tried it.
And on this way (1-3) you will definitely have some more questions. So welcome to SO.
Some users might see this as opinion-based-question but if you look closely, I am trying to explore use of Caffe as a purely testing platform as opposed to currently popular use as training platform.
Background:
I have installed all dependencies using Jetpack 2.0 on Nvidia TK1.
I have installed caffe and its dependencies successfully.
The MNIST example is working fine.
Task:
I have been given a convnet with all standard layers. (Not an opensource model)
The network weights and bias values etc are available after training. The training has not been done via caffe. (Pretrained Network)
The weights and bias are all in the form of MATLAB matrices. (Actually in a .txt file but I can easily write code to get them to be matrices)
I CANNOT do training of this network with caffe and must used the given weights and bias values ONLY for classification.
I have my own dataset in the form of 32x32 pixel images.
Issue:
In all tutorials, details are given on how to deploy and train a network, and then use the generated .proto and .caffemodel files to validate and classify. Is it possible to implement this network on caffe and directly use my weights/bias and training set to classify images? What are the available options here? I am a caffe-virgin so be kind. Thank you for the help!
The only issue here is:
How to initialize caffe net from text file weights?
I assume you have a 'deploy.prototxt' describing the net's architecture (layer types, connectivity, filter sizes etc.). The only issue remaining is how to set the internal weights of caffe.Net to pre-defined values saved as text files.
You can get access to caffe.Net internals, see net surgery tutorial on how this can be done in python.
Once you are able to set the weights according to your text file, you can net.save(...) the new weights into a binary caffemodel file to be used from now on. You do not have to train the net if you already have trained weights, and you can use it for generating predictions ("test").
If I have a video dataset of a specific action , how could I use them to train a classifier that could be used later to classify this action.
The question is very generic. In general, there is no foul proof way of training a classifier that will work for everything. It highly depends on the data you are working with.
Here is the 'generic' pipeline:
extract features from the video
label your features (positive for the action you are looking for; negative otherwise)
split your data into 2 (or 3) sets. One for training, one for testing and the other optionally for validation
train a classifier on the labeled examples (e.g. SVM, Neural Network, Nearest Neighbor ...)
validate the results on the validation data, if that is appropriate for the algorithm
test on data you haven't used for training.
You can start with some machine learning tools here http://www.cs.waikato.ac.nz/ml/weka/
Make sure you never touch the test data for any other purposes than testing
Good luck
Almost 10 years later, here's an updated answer.
Set up a camera and collect raw video data
Save it somewhere in form of single frames. Do this yourself locally or using a cloud bucket or use a service like Sieve API. Helpful repo linked here.
Export from Sieve or cloud bucket to get data labeled. Do this yourself or using some service like Scale Rapid.
Split your dataset into train, test, and validation.
Train a classifier on the labeled samples. Use transfer learning over some existing model and fine-tune just the last few layers.
Run your model over the test set after each training epoch and save the one with the best test set performance.
Evaluate your model at the end using the validation set.
There are many repos that can help you get started: https://github.com/weiaicunzai/awesome-image-classification
The two things that can help you ensure best results include 1. high quality labeled data and 2. a diverse, curated dataset. That's what Sieve can help with!